Microsoft Technology Licensing, LLC

Osbert Bastani

Antonio Criminisi

Dimitrios Vytiniotis

Aditya Vithal Nori

Leonidas Lampropoulos

A training engine is described which has a memory arranged to access a neural network image classifier, the neural network image classifier having been trained using a plurality of training images from an input space, the training images being labeled for a plurality of classes. The training engine has an adversarial example generator which computes a plurality of adversarial images by, for each adversarial image, searching a region in the input space around one of the training images, the region being one in which the neural network is linear, to find an image which is incorrectly classified into the plurality of classes by the neural network. The training engine has a processor which further trains the neural network image classifier using at least the adversarial images.

Growing community of inventors

Stanford, CA, United States of America

Osbert Bastani